{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RTP7CQV6VYMD452QDUD6MIN66Q","short_pith_number":"pith:RTP7CQV6","schema_version":"1.0","canonical_sha256":"8cdff142beae183e77501d07e621bef42307bf3376a01174e3880e254f96d040","source":{"kind":"arxiv","id":"2008.10150","version":2},"attestation_state":"computed","paper":{"title":"Contrastive learning, multi-view redundancy, and linear models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Akshay Krishnamurthy, Christopher Tosh, Daniel Hsu","submitted_at":"2020-08-24T01:31:47Z","abstract_excerpt":"Self-supervised learning is an empirically successful approach to unsupervised learning based on creating artificial supervised learning problems. A popular self-supervised approach to representation learning is contrastive learning, which leverages naturally occurring pairs of similar and dissimilar data points, or multiple views of the same data. This work provides a theoretical analysis of contrastive learning in the multi-view setting, where two views of each datum are available. The main result is that linear functions of the learned representations are nearly optimal on downstream predic"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2008.10150","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-24T01:31:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0792f05fa0ea43e9bbc6bbc550106dcadfd985e29601f2c4e0468fc7ad3b4835","abstract_canon_sha256":"57257c5d3344c124feb1ad87a70ef220f8885332243c65227bec50a67d9f2723"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:13.447757Z","signature_b64":"tC6KO9D+M4BRYAyhtZYj+JzNj9x6sIDMlD8N43XoTccMfdLaqVyA4w4igHxn4WEcWv2X93mre8JbmpLl+rm9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cdff142beae183e77501d07e621bef42307bf3376a01174e3880e254f96d040","last_reissued_at":"2026-07-05T02:32:13.447194Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:13.447194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive learning, multi-view redundancy, and linear models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Akshay Krishnamurthy, Christopher Tosh, Daniel Hsu","submitted_at":"2020-08-24T01:31:47Z","abstract_excerpt":"Self-supervised learning is an empirically successful approach to unsupervised learning based on creating artificial supervised learning problems. A popular self-supervised approach to representation learning is contrastive learning, which leverages naturally occurring pairs of similar and dissimilar data points, or multiple views of the same data. This work provides a theoretical analysis of contrastive learning in the multi-view setting, where two views of each datum are available. The main result is that linear functions of the learned representations are nearly optimal on downstream predic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.10150","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2008.10150/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2008.10150","created_at":"2026-07-05T02:32:13.447251+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.10150v2","created_at":"2026-07-05T02:32:13.447251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.10150","created_at":"2026-07-05T02:32:13.447251+00:00"},{"alias_kind":"pith_short_12","alias_value":"RTP7CQV6VYMD","created_at":"2026-07-05T02:32:13.447251+00:00"},{"alias_kind":"pith_short_16","alias_value":"RTP7CQV6VYMD452Q","created_at":"2026-07-05T02:32:13.447251+00:00"},{"alias_kind":"pith_short_8","alias_value":"RTP7CQV6","created_at":"2026-07-05T02:32:13.447251+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RTP7CQV6VYMD452QDUD6MIN66Q","json":"https://pith.science/pith/RTP7CQV6VYMD452QDUD6MIN66Q.json","graph_json":"https://pith.science/api/pith-number/RTP7CQV6VYMD452QDUD6MIN66Q/graph.json","events_json":"https://pith.science/api/pith-number/RTP7CQV6VYMD452QDUD6MIN66Q/events.json","paper":"https://pith.science/paper/RTP7CQV6"},"agent_actions":{"view_html":"https://pith.science/pith/RTP7CQV6VYMD452QDUD6MIN66Q","download_json":"https://pith.science/pith/RTP7CQV6VYMD452QDUD6MIN66Q.json","view_paper":"https://pith.science/paper/RTP7CQV6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.10150&json=true","fetch_graph":"https://pith.science/api/pith-number/RTP7CQV6VYMD452QDUD6MIN66Q/graph.json","fetch_events":"https://pith.science/api/pith-number/RTP7CQV6VYMD452QDUD6MIN66Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RTP7CQV6VYMD452QDUD6MIN66Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RTP7CQV6VYMD452QDUD6MIN66Q/action/storage_attestation","attest_author":"https://pith.science/pith/RTP7CQV6VYMD452QDUD6MIN66Q/action/author_attestation","sign_citation":"https://pith.science/pith/RTP7CQV6VYMD452QDUD6MIN66Q/action/citation_signature","submit_replication":"https://pith.science/pith/RTP7CQV6VYMD452QDUD6MIN66Q/action/replication_record"}},"created_at":"2026-07-05T02:32:13.447251+00:00","updated_at":"2026-07-05T02:32:13.447251+00:00"}